Context-Aware Computing Research Papers - Academia.edu (original) (raw)

Ubiquitous Computing promises seamless access to a wide range of applications and Internet-based services from anywhere, at anytime, and using any device. In this scenario, new challenges for the practice of software development arise: Applications and services must keep a coherent behavior, a proper appearance, and must adapt to a plenty of contextual usage requirements and hardware aspects. Especially, due to its interactive nature, the interface content of Web applications must adapt to a large diversity of devices and contexts. In order to overcome such obstacles, this work introduces an innovative methodology for content adaptation of Web 2.0 interfaces. The basis of our work is to combine static adaption — the implementation of static Web interfaces; and dynamic adaptation — the alteration, during execution time, of static interfaces so as for adapting to different contexts of use. In hybrid fashion, our methodology benefits from the advantages of both adaptation strategies — ...

Handheld computers are increasingly being used by hospital workers. With the integration of wireless networks into hospital information systems, handheld computers can provide the basis for a pervasive computing hospital environment; to develop this, designers need empirical information to understand how hospital workers interact with information while moving around. To characterize the medical phenomena we report the results of a workplace study conducted in a hospital. We found that individuals spend about half of their time at their base location, where most of their interactions occur. On average, our informants spent 23% of their time performing information management tasks, followed by coordination (17.08%), clinical case assessment (15.35%) and direct patient care (12.6%). We discuss how our results offer insights into the design of pervasive computing technology, and directions for further research and development in this field such as transferring information between heterogeneous devices and integration of the physical and digital domains.

The development of systems capable of recognizing and categorising emotions is of interest to researchers in various scientific areas including artificial intelligence. The traditional notion that emotions and rationality are two separate realms has gradually been challenged. The work of neurologists has shown the strong relationship between emotional episodes and the way humans think and act. Furthermore, emotions not only regulate human decisions but could also contribute to a more satisfactory response to the environment, i.e., faster and more precise actions. In this paper an analysis of physiological signals employed in real-time emotion detection is presented in the context of Intelligent Inhabited Environments (IIE). Two studies were performed to investigate whether physical exertion has a significant effect on bodily signals stemming from emotional episodes with subjects having various degrees of affect intensity: 1) a statistical analysis using the Wilcoxon Test, and 2) a cluster analysis using the Davies- Bouldin Index. Preliminary results demonstrated that the heart rate and skin resistance consistently showed similar changes regardless of the physical stimuli while blood volume pressure did not show a significant change. It was also found that neither physical stress nor affect intensity played a role in the separation of neutral and non-neutral emotional states.

- by Victor Callaghan and +1
- •
- Instrumentation Engineering, Bioinformatics, Physiology, Human Physiology
- by Béat Hirsbrunner
- •
- Ubiquitous Computing, Kinetics, Pervasive Computing, Context-Aware Computing

— It is no surprise that the notion of situation is key to situation awareness. The development of the discipline can thus benefit from careful analysis of the notion. In this paper, we approach this by proposing an ontology of situations and scenes. The main contribution of this ontology is that it accounts for how situations progress in time changing qualitatively, constituting what we call scenes. The ontology is built by reusing basic elements from the Unified Foundational Ontology (UFO). It addresses objects, occurrences, and their formal relations to situations and scenes. We use the theory of embodiment proposed by the philosopher Kit Fine to explicate how scenes and situations form wholes constituted of parts.

Altered states of consciousness (ASC) can be represented in video games through appropriate use of sound and computer graphics. Our research seeks to establish systematic methods for simulating ASC using computer sound and graphics, to improve the realism of ASC representations in video game engines. Quake Delirium is a prototype ‘ASC Simulation’ that we have created by modifying the video game Quake. Through automation of various graphical parameters that represent the conscious state of the game character, hallucinatory ASC are represented. While the initial version of Quake Delirium utilised a pre-determined automation path to produce these changes, we propose that immersion may be improved by providing the user with a ‘passive’ method of control, using a brain-computer interface (BCI). In this initial trial, we explore the use of a consumer-grade electroencephalograph (EEG) headset for this purpose. Keywords—Altered States of Consciousness; Video Games; Brain-Computer Interface ...

The context of an interactive system is not a single, unified entity. As multiple users interact with a system, engaging in multiple tasks in multiple environments, the nature of the context changes. This research proposes a framework for managing context, the Context-influence Framework. The Context-Influence Framework defines such a system as having multiple contexts, each associated with a particular combination of users and use of the system. These combinations, called "Use Subsystems," are affected by contextual Influences. Influences provide a means of standardizing and sharing contextual information within a team. For capturing contextual influence, context itself is divided into "Domains," areas of interest from which elements of context can be described. Once contextual Influences are captured and described, the descriptions of the contexts themselves can be managed and manipulated through the use of three hierarchies: People, Activity and Environment.

- by Eric Swanson and +1
- •
- Context-Aware Computing, User Interaction, Area of Interest, Contextual Information

The field of sensor fusion is well developed, but approaches to describing the confidence one ought to have in the fused result as a function of the confidence one has in the individual measurements is not. This speculative paper is intended to stimulate discussion in the robotics and instrumentation communities regarding how to approach "confidence fusion" in a way that can be practically applied in robotics applications and is intuitively satisfying with respect our feelings regarding how confidence in measurements ought to propagate. Preliminary ideas are developed in the context of a scenario wherein two one-bitoutput sensors in which we have different confidence are used together. The results are compared with numerical experiments simulating a real-life experiment that we have described in the field of sensor fusion for context-aware computing.

- by Huadong Wu and +1
- •
- Robotics, Computational Modeling, Context-Aware Computing, Robots

Bạn sẽ làm gì với một số vốn ít ỏi? Bạn muốn kinh doanh nhưng chưa biết bắt đầu từ đâu, lựa chọn sản phẩm nào, hay số vốn còn khá khiêm tốn? Với xu hướng ngày nay thì ít vốn bạn vẫn có thể kinh doanh tốt, bạn chỉ cần trang bị cho mình một chút kinh nghiệm và kiến thức thôi. Ý tưởng kinh doanh ít vốn nảy sinh khi mạng xã hội bắt đầu phát triển, từ đó bạn có thể bán hàng qua các kênh mạng xã hội mà không cần đầu tư vào cửa hàng, nhập nhiều hàng hóa mà số lượng khách hàng biết tới bạn lại rất nhiều. Chính vì thế mà xu hướng kinh doanh Online ngày càng phát triển, bạn là người đi sau vậy cần lưu ý những điểm sau để ý tưởng kinh doanh ít vốn của bạn thành công. Ý tưởng kinh doanh ít vốn 1. LỰA CHỌN SẢN PHẨM Hiện nay, hàng hóa được bán Online rất đa dạng và phong phú từ những món hàng thường ngày như: quần áo, giày dép, túi xách, nước hoa, đồng hồ… ngoài ra là những sản phẩm độc đáo như: đồ handmade. Chính vì thế nếu bạn muốn sự cạnh tranh thấp hãy lựa chọn những sản phẩm như sau: + Đồ thời trang nhưng độc và lạ + Sản phẩm handmade + Những món hàng chỉ bạn mới có Món ngon: Cháo bí ngô converted by Web2PDFConvert.com

- by cuong manh
- •
- Agricultural Engineering, Agronomy, Agribusiness, Organic agriculture

In this work, we investigate how gamification can be integrated into work processes in the automotive industry. The contribution contains five parts: (1) An introduction showing how gamification has become increasingly common, especially in education, health and the service industry. (2) An analysis on the state of the art of gamified applications, discussing several best practices. (3) An analysis of the special requirements for gamification in production, regarding both external norms and the mindset of workers in this domain. (4) An overview of first approaches towards a gamification of production, focusing on solutions for impaired workers in sheltered work organizations. (5) A study with a focus group of instructors at two large car manufacturers. Based on the presentation of three potential designs for the gamification of production, the study investigates the general acceptance of gamification in modern production and determines which design is best suited for future implementations.

In today's society, a large number of mobile electronic devices are used on a regular basis. These devices often require a lot of settings to be made by the user. One way of minimizing this and introducing smartness into these devices is through the concept of context awareness. The purpose of this Master's thesis is to implement a context classifier on a commercially available PDA and to evaluate the feasibility of such an application.

- by Filip Bonnevier
- •
- Machine Learning, Audio Engineering, Audio Signal Processing, Mobile Technology

In the area of ambient intelligence there is a need to address user needs according with context features. Recently, the synergy between context aware computing and collaborative filtering is leading to enhance recommender systems with capabilities always nearer to user needs. Specifically, in the domain of tourism it is useful to proactively suggest right sets of attractive locations, events and so on. This work defines a context aware recommender system aimed at suggesting pertinent points of interest (POIs) to tourists. In particular, the approach is strongly based on the synergy between soft computing and data mining techniques. The general framework integrates user profiles, history of social networking and POIs data. Then by defining collaborative filtering approach on the history meaningful POIs are extracted. Indeed, soft computing techniques are mainly applied in order to support activity of unsupervised users and POIs classification. On the other hand, data mining techniques are exploited in order to extract rules able to associate user profile and context features with an eligible set of recommendable POIs. Experimental results show performance in terms of recommendations accuracy.

- by enrico fischetti
- •
- Data Mining, Social Networking, Ubiquitous Computing, Soft Computing

Although there already exist traditional metaphors influencing human-computer interaction (HCI) such as the human-human interaction metaphor, some applications emerging in areas from intelligent agents to wearable and context-aware computing have prompted the authors to identify a new metaphor implicitly emerging in HCI. This will be referred to as the conscious-subconscious (C-S) metaphor. The explicit elucidation of this C-S metaphor poises HCI to speak to and leverage research in philosophy and cognitive science pertaining to consciousness and cognition.

We investigate the correlation between wrist movement and freezing of the gait in Parkinsons disease. Detecting such freezes allows real-time monitoring to reduce the risk of falls in subjects with Parkinson’s. While most of research focuses on placing inertial sensors on lower limb, i.e., foot, ankle, thigh, lower back, we focus on the wrist as an alternative placement. Commonly worn accessories at the wrist such as watches or wristbands are easier to be accepted and worn by elderly users, in special subjects with motor problems. Experiments on data from 11 subjects show that freezing of gait episodes can be detected using the wrist movements, with a freeze hit-rate of 90% and 83% specificity in a subject-dependent evaluation scheme. This suggests that wrist sensors can be a feasible alternative to the cumbersome placement on the legs.

- by Arjun Raj
- •
- Computer Science, Algorithms, Computer Engineering, Wireless Communications

Sentient Computing provides computers with perception so that they can react and provide assistance to user activities. Physical spaces are made sentient when they are wired with networks of sensors capturing context data, which is communicated to computing devices spread through the environment. These devices interpret the information provided and react by performing the actions expected by the user. Among the types of context information provided by sensors, location has proven to be especially useful. Since location is an important context that changes whenever the user moves, a reliable location-tracking system is critical to many sentient applications. However, the sensor technologies used in indoor location tracking are expensive and complex to deploy, configure and maintain. These factors have prevented a wider adoption of Sentient Computing in our living and working spaces. This paper presents TRIP, a low-cost and easily deployable vision-based sensor technology addressing these issues. TRIP employs off-the-shelf hardware (low-cost CCD cameras and PCs) and printable 2-D circular markers for entity identification and location. The usability of TRIP is illustrated through the implementation of several sentient applications.

Ubiquitous computing defines a new paradigm in which devices with processing and communication capacity are embedded into everyday elements, providing services in a transparent way to users. It is possible to notice that this kind of computing has a strong connection with physical world features, as well as those presented by its users profiles. In this way, if ubiquitous systems are capable of using as input relevant information about entities (e.g., people, places or objects) related to the application, they can provide services that are more appropriate, dynamic and optimized, increasing the user satisfaction and minimizing resource consumption, such as energy, processing, communication, among others. Such information is called context and represents the basic input element for context-aware computing. The goal of this short course is to discuss research trends on the ubiquitous context-aware field, presenting and analyzing the research performed on specific challenges. Such proposal presents interesting solutions to problems ranging from physical aspects of wireless communication to the design of applications available to the users.

- by Teste teste
- •
- Ubiquitous Computing, Context-Aware Computing, Context Aware, Wireless Communication

We looked through all the latest technology that could be used in conjunction with your smartphone, something that could really get shoppers engaged and interested in the experience and we found that in Gimbal, a software platform that can help shape our users shopping patterns through using the technology in their phone best suited our needs. Using this technology, the smartphone will be used as a tool to gain a privacy enhanced peek into user’s interests, habits and personality, therefore our application will slowly get to know the user and recommend items thorough push messages that users may have a need for.

- by JP Gallagher
- •
- Marketing, Context-Aware Computing, Cloud Computing, Location Based Applications

___ In Tic-Tac-Toe of the classic game is built on computer-based flat form using python as a part of case study project using Artificial Intelligent techniques. The primary goal for this project is to create a computer artificial intelligent based on Tic-Tac-Toe 4x4 game that show two players on who will win and who will lose the game accordingly, using the standard Minimax algorithm, it was adopted and modified as a subset of rules from best gameplay practices: (1) attempt to win, (2) endeavor to keep a misfortune, (3) make a key move, and (4) make an irregular move. To make the game more fun and more winnable at easier difficulty levels, probabilities are introduced that the computer would find a valuable move and ignore it. In the end, the computer artificial intelligent uses a simple, lightweight decision tree to choose its next move, and the gameplay is fast, balanced, and enjoyable. furthermore, in the winning strategy in a chess game by means of symbolic model checking, and demonstrate the winning strategy in tic-tac-toe game through the symbolic model checking tool improved with the verification algorithm for winning strategy.

Context-awareness is an essential component of systems developed in areas like Intelligent Environments, Pervasive & Ubiquitous Computing and Ambient Intelligence. In these emerging fields, there is a need for computerized systems to have a higher understanding of the situations in which to provide services or functionalities, to adapt accordingly. The literature shows that researchers modify existing engineering methods in order to better fit the needs of context-aware computing. These efforts are typically disconnected from each other and generally focus on solving specific development issues. We encourage the creation of a more holistic and unified engineering process that is tailored for the demands of these systems. For this purpose, we study the state-of-the-art in the development of context-aware systems, focusing on: A) Methodologies for developing context-aware systems, analysing the reasons behind their lack of adoption and features that the community wish they can use. B) Context-aware system engineering challenges and techniques applied during the most common development stages; C) Context-aware systems conceptualization;

- by Juan Carlos Augusto
- •
- Context-Aware Computing

Proceedings of the 2nd international conference on telecommunications and remote sensing, ICTRS 2013

Seminar talk delivered at a seminar organised by infogroep.

- by Beat Signer
- •
- Information Systems, Engineering, Computer Science, Algorithms

Micro-location is the process of locating any entity with high accuracy (possibly in centimeters), while geofencing is the process of creating a virtual fence around a so-called Point of Interest (PoI). In this paper, we present an insight into various micro-location enabling technologies and services. We also discuss how these can accelerate the incorporation of Internet of Things (IoT) in smart buildings. We argue that micro-location based location-aware solutions can play a significant role in facilitating the tenants of an IoT equipped smart building. Also, such advanced technologies will enable the smart building control system through minimal actions performed by the tenants. We also highlight the existing and envisioned services to be provided by using micro-location enabling technologies. We describe the challenges and propose some potential solutions such that micro-location enabling technologies and services are thoroughly integrated with IoT equipped smart building.

- by Fahim Zafari and +1
- •
- E Marketing, The Internet of Things, Context-Aware Computing, Internet of Things

The increasing use of multisensory devices has caused a growing interest the area of Distributed Systems in CENIDET. In recent years many context-aware recommendation systems have been developed. These services are based in the user profile; therefore, they provide personalized information. The recommendation systems involve different technologies to capture environmental data, such as NFC, RFID, GPS, Wi-Fi and so on. In recent years, Augmented Reality has caused a big impact in the development of this kind of services. This technology is able to include virtual objects into the real world using a multisensory device.
In this thesis project, an indoor-outdoor navigation system was developed. The system implements an interface through Augmented Reality and the interface allows the user to navigate inside and outside of an organization and interact with contextual information. This information can be a place, an event, a contact, a notice and so on. Hence, a model of identification of points of interest by origin-destination nodes for navigation and nodes of interest (place, person, event, etc.) was developed.
Each node contains a poster of information; there are two types of posters: the first for interaction service, which offers the service of navigation, and the second one the contextual information service. In the navigation system, a service of generation route algorithm and the ADA standard were implemented. This service and standard will be able to determine whether a selected route is accessible or not, providing support to users with disabilities.
Finally, in this project, a system able to show contextual information to guide users inside and outside an organization (indoor-outdoor navigation) through augmented reality technologies in multisensory devices was developed.

Context awareness plays an important role in recent smart environments and embedded interactions. In order to increase user satisfaction and acceptance, these context-aware solutions should be controllable by end users. Over the last few years we have therefore seen an emerging trend towards visual programming tools for context-aware applications based on simple "IF this THEN that" rules. However, existing solutions often do not support the simple reuse of the "this" part in order to define more sophisticated rules. Given that the desired level of control varies among individuals, we propose a unified multi-layered context modelling approach distinguishing between end users, expert users and programmers. Our Context Modelling Toolkit (CMT) consists of the necessary context modelling concepts and offers a rule-based context processing engine. We further illustrate how end users and expert users might interact with the CMT framework. Finally, we highlight some advantages of our Context Modelling Toolkit by discussing a number of use cases.

- by Lars Van Holsbeeke and +1
- •
- Information Systems, Engineering, Computer Science, Software Engineering

The technology of Smart Homes (SH), as an instance of ambient assisted living technologies, is designed to assist the homes’ residents accomplishing their daily-living activities and thus having a better quality of life while preserving their privacy. A SH system is usually equipped with a collection of inter-related software and hardware components to monitor the living space by capturing the behaviour of the resident and understanding his activities. By doing so the system can inform about risky situations and take actions on behalf of the resident to his satisfaction. The present survey will address technologies and analysis methods and bring examples of the state of the art research studies in order to provide background for the research community. In particular, the survey will expose infrastructure technologies such as sensors and communication platforms along with artificial intelligence techniques used for modeling and recognizing activities. A brief overview of approaches used to develop Human–Computer interfaces for SH systems is given. The survey also highlights the challenges and research trends in this area.

- by Mohsen Amiribesheli
- •
- Artificial Intelligence, Machine Learning, Dementia, Pervasive Computing

Contextual or dependent information technologies are projected as the new paradigm of interaction between the user and his or her environment. Systems where the user will receive feedback from contextual information depending on where it is located.
These services will, among other things, do the activities scheduled on his or her agenda, which are related to a specific location, i.e. define a relationship between space and time, unlike traditional agendas which only administer timeless activities.
This project presents a novel system that uses self-identification technologies such as RFID and QRCodes, and mobile phones with the Android operating system for locating users inside multi-level buildings and in campus-type areas, i.e. with several buildings. The association also offers real-world objects to the information system by means of self-identification using RFID and QRCodes.

- by Amina Cherouana
- •
- Computer Science, Context-Aware Computing, Business Management

Tactical networking environments present many challenges in terms of bandwidth, latency, reliability, stability, and connectivity. Sensors can today generate very large data sets that exceed the ability of tactical networks to transfer and disseminate them in a timely manner. Furthermore, the desire to cover larger areas with persistent sensing capabilities, have resulted in the widescale deployment of inexpensive sensors, further widening the gap between the volume of information that is generated and the subset that can successfully be delivered to consumers. This article explores the notion of determining the value of information in order to prioritize and filter information that is disseminated over these tactical networks, focusing on the dissemination of information to and from dismounted soldiers in a battlefield environment. This is a promising approach to mitigate the constraints of tactical networks and to reduce information overload on soldiers.

- by Giacomo Benincasa and +1
- •
- Mobile Ad Hoc Networks, Wireless Sensor Networks, Context-Aware Computing, Mobile Computing

Ubiquitous Computing is a paradigm containing the
characteristics to break away from the traditional desktop
computing system and turn to such computer systems where
everything is available & accessible everywhere through various
devices while keeping them effectively invisible. The
accomplishment of this vision requires a deep involvement of
multiple areas including software engineering. Software
engineering plays a major role in ubi-comp world; but the lack of
appropriate software engineering approaches is identified as a
major obstacle on the route to propose a general level framework
that should be adopted for all kinds of ubi-comp applications. The
very initial step which is still required for this vision is to identify all
potential software engineering challenges in the ubi-comp era. In
this paper we have made a survey of various ubi-comp applications
and extracted a number of software engineering challenges faced
by other researchers during the development of such applications.
This work provides a future direction for other researchers and
developers to make the process of providing an appropriate
framework for building ubi-comp application more effectively.

The International Journal of Computer Networks & Communications (IJCNC) is a bi monthly open access peer-reviewed journal that publishes articles which contribute new results in all areas of Computer Networks & Communications. The journal focuses on all technical and practical aspects of Computer Networks & data Communications. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on advanced networking concepts and establishing new collaborations in these areas.

Over the last decade, we have witnessed an emergence of Personal Information Management (PIM) solutions. Despite the fact that paper documents still form a significant part of our daily working activities, existing PIM systems usually support the organisation and re-finding of digital documents only. While physical document tracking solutions such as RFID- or computer vision-based systems are recently gaining some attention, they usually focus on the paper document tracking and offer limited support for re-finding activities. We present PimVis, a solution for exploring and re-finding digital and paper documents in so-called cross-media information spaces. The PimVis user interface enables a unified organisation of digital and paper documents through the creation of bidirectional links between the digital and physical information space. The presented personal cross-media information management solution further supports the extension with alternative document tracking techniques as well as augmented reality solutions. A formative PimVis evaluation revealed the high potential of fully integrated cross-media PIM solutions.

- by Sandra Trullemans and +2
- •
- Information Systems, Engineering, Computer Science, Algorithms

The current era of advanced display technologies, such as a head mounted displays, smart glasses and handheld devices, have supported the usage of mixed-reality and augmented reality concepts in smart educational classrooms. These advanced technologies have enabled enhanced collaboration and an interactive communication between distance learners and local learners. Being present’ is a key factor in both worlds (real and virtual) as it plays an important role in increasing the students’ collaborative engagement during the learning activity. However, few studies have considered how much using such immersive interfaces with various learning scenarios may ultimately affect learning outcomes, and whether students feel fully engaged or not in such environments. This work-in progress paper will demonstrate a MiRTLE+ prototype of how remote students can collaborate within mixed-reality environments by using an augmented reality approach. Secondly, it will explore the learning effectiveness based on the following factors: students’ presence, engagement, and immersion in smart environments. With regard to the learning task, we will consider a card game task to measure the learners’ progress as they progress from novice to expert player. To evaluate these factors, we utilise several existing frameworks which have been applied to our mixed-reality worlds

- by Victor Callaghan
- •
- Teaching and Learning, Educational Technology, E-learning, Science Education

Location Based Services (LBS) are applications that provide Users recommendations about services available based on the user's location. Location in this kind of systems is provided mainly through the use of geographic maps that currently have been focusing primarily in outdoor environments but nowadays are gradually moving towards indoor environments like malls, museums, public buildings and others.
Among this kind of systems We found Context Aware Recommendation Systems (CARS), which provide recommendations to users based on their context information, this context information may consist on user's location, changes on the environment, date and time of the day and any other relevant information for the interaction between users and the System, whereupon it is possible to characterize the state of the individual entities that interact with the System and the user, as well as the relationships between these entities, given as a result the possibility to provide more accurate recommendations to the user.
This thesis project focuses on indoor environments, here it is presented a system that allows the creation of draft maps for indoor environments making use of emerging technologies like Scalable Vector Graphics (SVG) and ontology models, which allows to add contextual information related with the infrastructure of this type of environments. Additionally, it is presented an algorithm that allows to find all passable routes in generated maps, which can be used to provide navigation services in a Contextual Recommender System.

Hospital workers are highly mobile; they are constantly changing location to perform their daily work, which includes visiting patients, locating resources, such as medical records, or consulting with other specialists. The information required by these specialists is highly dependent on their location. Access to a patient's laboratory results might be more relevant when the physician is near the patient's bed and not elsewhere. We describe a location-aware medical information system that was developed to provide access to resources such as patient's records or the location of a medical specialist, based on the user's location. The system is based on a handheld computer which includes a trained backpropagation neural-network used to estimate the user's location and a client to access information from the hospital information system that is relevant to the user's current location.

- by edgar martinez
- •
- Engineering, Algorithms, Context-Aware Computing, Location-Awareness

The recognition of human activities through sensors embedded in smart-phone devices, such as iPhone, is attracting researchers due to its relevance. The advances of this kind of technology are making possible the widespread and pervasiveness of sensing technology to take advantage of multiple sources of sensing to enrich users experience or to achieve proactive, context-aware applications and services. Human activity recognition and monitoring involves a continuing analysis of large amounts of data so, any increase or decrease in accuracy results in a wide variation in the number of activities correctly classi ed and incorrectly classi ed, so it is very important to increase the rate of correct classication. We have researched on a vector with 159 diferent features and on the vector subsets in order to improve the human activities recognition. We extracted features from the Magnitude of the Signal, the raw signal data, the vertical acceleration, the Horizontal acceleration, and the ltered Raw data. In the evaluation process we used the classi ers: Naive Bayes, K-Nearest Neighbor and Random Forest. The features were extracted using the java programming language and the evaluation was done with WEKA. The maximum accuracy was obtained, as expected, with Random Forest using all the 159 features. The best subset found has twelve features: the Pearson correlation between vertical acceleration and horizontal acceleration, the Pearson correlation between x and y, the Pearson correlation between x and z, the STD of acceleration z, the STD of digital compass y, the STD of digital compass z, the STD of digital compass x, the mean between axis, the energy of digital compass x, the mean of acceleration x, the mean of acceleration z, the median of acceleration z.

- by Nuno Cruz Silva
- •
- Machine Learning, Data Analysis, Context-Aware Computing, Health Systems

A relevant piece of information in many contextaware applications for wireless and mobile users is the user's current location. Knowledge of the position, when combined with the user preferences, permits efficient service (or product)... more

The transportation mode such as walking, cycling or on a train denotes an important characteristic of the mobile user’s context. In this paper, we propose an approach to infer a user’s mode of transportation based on the GPS sensors on their mobile devices, and knowledge of the underlying transportation network. The transportation network information considered includes real time bus locations, spatial rail and spatial bus stop information. We identify and derive the relevant features related to transportation network information to improve classification effectiveness. This approach can achieve over 93.5% accuracy for inferring various transportation modes including: car, bus, aboveground train, walking, bike, and stationary. Compared with existing methods, our approach improves the accuracy of detection by 17% for GPS only approach, and 9% for GPS with GIS models. This proposed technique is the first to distinguish between motorized transportation modes such as bus, car and aboveground train with such high accuracy. Additionally, if a user is travelling by bus, we provide further information about which particular bus the user is travelling on. Five different inference models including, Bayesian Net, Decision Tree, Random Forest, Naïve Bayesian and Multilayer Perceptron, are studied in the experiments. The final classification system is deployed and available to the public.

- by Leon Stenneth
- •
- Machine Learning, Ubiquitous Computing, Pattern Recognition, Pervasive Computing

Selective attention systems are found to be very interesting as well from theoretical point of view, as also as useful tools for many practical applications, such as analysis of large data sets, real time route planning for autonomic robots in dynamical environment, and dispersed sensor networks control. However up to date models of biological selective attention systems and other methods that realize similar functionality still have some drawbacks. Decision trees are easy to analyze by humans, but once created are hard to adapt to the changes in the system environment. The next example - statistical feature selection algorithms create solutions that use globally suboptimal feature sets, but in general they are not optimal from the point of view of single input vectors, and those algorithms are hard to apply in fast changing environments. This is why biologically founded neuronal selective attention systems seem to offer better properties for many possible applications. The only problem with neuronal selective attention systems is that their existing models implement artificial, centralized attention directing algorithms and in the effect they do not offer functionality observed in the nature. This is why there is still a need for analyzing properties of natural selective attention mechanisms, as well as for further exploration of possible models of biological neuronal selective attention systems.

- by Maciej Huk
- •
- Selective Attention, Context-Aware Computing, Artificial Neural Networks

This paper discusses our ongoing research on user interaction with autonomous mobile agents. The overarching project, DIADEM, involves the development of a (semi-)autonomous system that detects potential environmental hazards in heavily populated urban- industrial areas by using input from both a distributed sensor network and humans through their mobile devices. User experiments in this project will focus on social and affective issues in interacting with autonomous mobile agents (such as positioning of mobile agents in relation to the user, empathic interaction and user trust). We describe the project and research context for our studies.

- by Andi Winterboer and +1
- •
- Human Computer Interaction, Context-Aware Computing, Environmental Monitoring, Sensor networks

The last years have witnessed the emergence of a multitude of novel technologies and devices offering services and entertainment to the driver and passengers. Although this trend focused on supporting safety and comfort for the user, it also generates some undesirable consequences from the point of view of the user experience: it increases the number of functionalities available on the car but leads to an extensive automation of driving tasks which in turn decrease user experience and reduces the pleasure of driving. This paper discusses a novel approach to safe driving while improving the vehicular user experiences through innovative interaction possibilities. Context-awareness and multimodal interactions (e.g., gestures and voice) are used to provide natural and personal interaction, and proactivity. Several scenarios are presented and discussed.

- by Maurizio Caon and +2
- •
- Automotive Systems Engineering, Human Computer Interaction, Context-Aware Computing, Natural User Interfaces